[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemacs-commit] qemacs charset.c charsetmore.c kmaptoqe.c ligto...
|
From: |
Charlie Gordon |
|
Subject: |
[Qemacs-commit] qemacs charset.c charsetmore.c kmaptoqe.c ligto... |
|
Date: |
Sat, 01 Mar 2014 22:37:26 +0000 |
CVSROOT: /sources/qemacs
Module name: qemacs
Changes by: Charlie Gordon <chqrlie> 14/03/01 22:37:26
Modified files:
. : charset.c charsetmore.c kmaptoqe.c ligtoqe.c
charsetjis.c cptoqe.c ligatures qe.h
Log message:
Add charset probing functions
* add QECharset method probe_func() to test charset likelihood
* probe function is not used for automatic charset detection yet
* fix kmaptoqe.c to use stable sorting and make kmaps reproducible
* fix ligtoqe.c to use stable sorting and make ligatures reproducible
CVSWeb URLs:
http://cvs.savannah.gnu.org/viewcvs/qemacs/charset.c?cvsroot=qemacs&r1=1.32&r2=1.33
http://cvs.savannah.gnu.org/viewcvs/qemacs/charsetmore.c?cvsroot=qemacs&r1=1.18&r2=1.19
http://cvs.savannah.gnu.org/viewcvs/qemacs/kmaptoqe.c?cvsroot=qemacs&r1=1.11&r2=1.12
http://cvs.savannah.gnu.org/viewcvs/qemacs/ligtoqe.c?cvsroot=qemacs&r1=1.9&r2=1.10
http://cvs.savannah.gnu.org/viewcvs/qemacs/charsetjis.c?cvsroot=qemacs&r1=1.6&r2=1.7
http://cvs.savannah.gnu.org/viewcvs/qemacs/cptoqe.c?cvsroot=qemacs&r1=1.16&r2=1.17
http://cvs.savannah.gnu.org/viewcvs/qemacs/ligatures?cvsroot=qemacs&rev=1.2
http://cvs.savannah.gnu.org/viewcvs/qemacs/qe.h?cvsroot=qemacs&r1=1.142&r2=1.143
Patches:
Index: charset.c
===================================================================
RCS file: /sources/qemacs/qemacs/charset.c,v
retrieving revision 1.32
retrieving revision 1.33
diff -u -b -r1.32 -r1.33
--- charset.c 10 Feb 2014 20:29:26 -0000 1.32
+++ charset.c 1 Mar 2014 22:37:26 -0000 1.33
@@ -119,6 +119,7 @@
QECharset charset_raw = {
"raw",
"binary|none",
+ NULL,
decode_raw_init,
decode_8bit,
encode_raw,
@@ -132,6 +133,46 @@
/********************************************************/
/* 8859-1 */
+static int probe_8859_1(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + size;
+ uint32_t c;
+ int count_spaces, count_lines, count_high;
+
+ count_spaces = count_lines = count_high = 0;
+
+ while (p < p_end) {
+ c = p[0];
+ p += 1;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c < 0x7F) {
+ continue;
+ } else
+ if (c < 0x80) {
+ return 0;
+ } else {
+ count_high++;
+ }
+ }
+ if (count_spaces | count_lines)
+ return 1;
+ else
+ return 0;
+}
+
static void decode_8859_1_init(CharsetDecodeState *s)
{
s->table = table_idem;
@@ -150,6 +191,7 @@
QECharset charset_8859_1 = {
"8859-1",
"ISO-8859-1|iso-ir-100|latin1|l1|819",
+ probe_8859_1,
decode_8859_1_init,
decode_8bit,
encode_8859_1,
@@ -181,6 +223,7 @@
QECharset charset_vt100 = {
"vt100",
NULL,
+ NULL,
decode_vt100_init,
decode_8bit,
encode_vt100,
@@ -207,6 +250,7 @@
static QECharset charset_7bit = {
"7bit",
"us-ascii|ascii|7-bit|iso-ir-6|ANSI_X3.4|646",
+ NULL,
decode_8859_1_init,
decode_8bit,
encode_7bit,
@@ -316,6 +360,80 @@
return uq - dest;
}
+static int probe_utf8(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + size;
+ uint32_t c;
+ int count_spaces, count_lines, count_utf8;
+
+ count_spaces = count_lines = count_utf8 = 0;
+
+ while (p < p_end) {
+ c = p[0];
+ p += 1;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c < 0x7F) {
+ continue;
+ } else
+ if (c < 0xc0) {
+ return 0;
+ } else
+ if (c < 0xe0) {
+ if (p[0] < 0x80 || p[0] > 0xbf)
+ return 0;
+ count_utf8++;
+ p += 1;
+ } else
+ if (c < 0xf0) {
+ if (p[0] < 0x80 || p[0] > 0xbf || p[1] < 0x80 || p[1] > 0xbf)
+ return 0;
+ count_utf8++;
+ p += 2;
+ } else
+ if (c < 0xf8) {
+ if (p[0] < 0x80 || p[0] > 0xbf || p[1] < 0x80 || p[1] > 0xbf
+ || p[2] < 0x80 || p[2] > 0xbf)
+ return 0;
+ count_utf8++;
+ p += 3;
+ } else
+ if (c < 0xfc) {
+ if (p[0] < 0x80 || p[0] > 0xbf || p[1] < 0x80 || p[1] > 0xbf
+ || p[2] < 0x80 || p[2] > 0xbf || p[3] < 0x80 || p[3] > 0xbf)
+ return 0;
+ count_utf8++;
+ p += 4;
+ } else
+ if (c < 0xfe) {
+ if (p[0] < 0x80 || p[0] > 0xbf || p[1] < 0x80 || p[1] > 0xbf
+ || p[2] < 0x80 || p[2] > 0xbf || p[3] < 0x80 || p[3] > 0xbf
+ || p[4] < 0x80 || p[4] > 0xbf)
+ return 0;
+ count_utf8++;
+ p += 5;
+ } else {
+ return 0;
+ }
+ }
+ if (count_spaces | count_lines | count_utf8)
+ return 1;
+ else
+ return 0;
+}
+
static void decode_utf8_init(CharsetDecodeState *s)
{
s->table = table_utf8;
@@ -432,6 +550,7 @@
QECharset charset_utf8 = {
"utf-8",
"utf8",
+ probe_utf8,
decode_utf8_init,
decode_utf8_func,
encode_utf8,
@@ -445,6 +564,44 @@
/********************************************************/
/* UCS2/UCS4 */
+static int probe_ucs2le(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + (size & ~1);
+ uint32_t c;
+ int count_spaces, count_lines;
+
+ if (size & 1)
+ return 0;
+
+ count_spaces = count_lines = 0;
+
+ while (p < p_end) {
+ c = (p[0] << 0) | (p[1] << 8);
+ p += 2;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c >= 0x10000) {
+ return 0;
+ }
+ }
+ if (count_spaces | count_lines)
+ return 1;
+ else
+ return 0;
+}
+
static void decode_ucs_init(CharsetDecodeState *s)
{
s->table = table_none;
@@ -543,6 +700,44 @@
return (const u8 *)lp - buf;
}
+static int probe_ucs2be(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + (size & ~1);
+ uint32_t c;
+ int count_spaces, count_lines;
+
+ if (size & 1)
+ return 0;
+
+ count_spaces = count_lines = 0;
+
+ while (p < p_end) {
+ c = (p[0] << 8) | (p[1] << 0);
+ p += 2;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c >= 0x10000) {
+ return 0;
+ }
+ }
+ if (count_spaces | count_lines)
+ return 1;
+ else
+ return 0;
+}
+
static int decode_ucs2be(CharsetDecodeState *s)
{
/* XXX: should handle surrogates */
@@ -624,6 +819,7 @@
QECharset charset_ucs2le = {
"ucs2le",
"utf16le|utf-16le",
+ probe_ucs2le,
decode_ucs_init,
decode_ucs2le,
encode_ucs2le,
@@ -637,6 +833,7 @@
QECharset charset_ucs2be = {
"ucs2be",
"ucs2|utf16|utf-16|utf16be|utf-16be",
+ probe_ucs2be,
decode_ucs_init,
decode_ucs2be,
encode_ucs2be,
@@ -647,6 +844,44 @@
2, 0, 0, 10, 0, 0, NULL, NULL,
};
+static int probe_ucs4le(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + (size & ~3);
+ uint32_t c;
+ int count_spaces, count_lines;
+
+ if (size & 3)
+ return 0;
+
+ count_spaces = count_lines = 0;
+
+ while (p < p_end) {
+ c = (p[0] << 0) | (p[1] << 8) | (p[2] << 16) | (p[3] << 24);
+ p += 4;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c >= 0x10000) {
+ return 0;
+ }
+ }
+ if (count_spaces | count_lines)
+ return 1;
+ else
+ return 0;
+}
+
static int decode_ucs4le(CharsetDecodeState *s)
{
const u8 *p;
@@ -739,6 +974,44 @@
return (const u8 *)lp - buf;
}
+static int probe_ucs4be(__unused__ QECharset *charset, const u8 *buf, int size)
+{
+ static const uint32_t magic = (1 << '\b') | (1 << '\t') | (1 << '\f') |
+ (1 << '\n') | (1 << '\r') | (1 << '\033') |
+ (1 << 0x0e) | (1 << 0x0f) | (1 << 0x1f);
+ const u8 *p = buf;
+ const u8 *p_end = p + (size & ~3);
+ uint32_t c;
+ int count_spaces, count_lines;
+
+ if (size & 3)
+ return 0;
+
+ count_spaces = count_lines = 0;
+
+ while (p < p_end) {
+ c = (p[0] << 24) | (p[1] << 16) | (p[2] << 8) | (p[3] << 0);
+ p += 4;
+ if (c <= 32) {
+ if (c == ' ')
+ count_spaces++;
+ else
+ if (c == '\n')
+ count_lines++;
+ else
+ if (!(magic & (1 << c)))
+ return 0;
+ } else
+ if (c >= 0x10000) {
+ return 0;
+ }
+ }
+ if (count_spaces | count_lines)
+ return 1;
+ else
+ return 0;
+}
+
static int decode_ucs4be(CharsetDecodeState *s)
{
const u8 *p;
@@ -818,6 +1091,7 @@
QECharset charset_ucs4le = {
"ucs4le",
"utf32le|utf-32le",
+ probe_ucs4le,
decode_ucs_init,
decode_ucs4le,
encode_ucs4le,
@@ -831,6 +1105,7 @@
QECharset charset_ucs4be = {
"ucs4be",
"ucs4|utf32|utf-32|utf32be|utf-32be",
+ probe_ucs4be,
decode_ucs_init,
decode_ucs4be,
encode_ucs4be,
@@ -1100,9 +1375,37 @@
*eol_typep = eol_type;
}
-/* detect the charset. Actually only UTF8 is detected */
QECharset *detect_charset(const u8 *buf, int size, EOLType *eol_typep)
{
+#if 0
+ QECharset *charset;
+
+ /* Try and determine charset */
+ /* CG: should iterate over charsets with probe function and score */
+ charset = &charset_utf8;
+ if (size > 0) {
+ if (charset_utf8.probe_func(&charset_utf8, buf, size))
+ charset = &charset_utf8;
+ else
+ if (charset_ucs4le.probe_func(&charset_ucs4le, buf, size))
+ charset = &charset_ucs4le;
+ else
+ if (charset_ucs4be.probe_func(&charset_ucs4be, buf, size))
+ charset = &charset_ucs4be;
+ else
+ if (charset_ucs2le.probe_func(&charset_ucs2le, buf, size))
+ charset = &charset_ucs2le;
+ else
+ if (charset_ucs2be.probe_func(&charset_ucs2be, buf, size))
+ charset = &charset_ucs2be;
+ else
+ charset = &charset_8859_1;
+ /* CG: should distinguish charset_8859_1, charset_raw and
+ * charset_auto */
+ }
+ return charset;
+#else
+ /* detect the charset. Actually only UTF8 is detected */
int i, l, c, has_utf8, has_binary;
has_utf8 = 0;
@@ -1211,6 +1514,7 @@
#endif
/* XXX: should use a state variable for default charset */
return &charset_utf8;
+#endif
}
/********************************************************/
Index: charsetmore.c
===================================================================
RCS file: /sources/qemacs/qemacs/charsetmore.c,v
retrieving revision 1.18
retrieving revision 1.19
diff -u -b -r1.18 -r1.19
--- charsetmore.c 1 Mar 2014 21:57:28 -0000 1.18
+++ charsetmore.c 1 Mar 2014 22:37:26 -0000 1.19
@@ -48,6 +48,7 @@
static QECharset charset_8859_2 = {
"8859-2",
"ISO-8859-2|iso-ir-101|latin2|l2|iso-latin2",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -90,6 +91,7 @@
static QECharset charset_8859_3 = {
"8859-3",
"ISO-8859-3",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -132,6 +134,7 @@
static QECharset charset_8859_4 = {
"8859-4",
"ISO-8859-4|iso-ir-110|latin4|l4|iso-latin4",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -174,6 +177,7 @@
static QECharset charset_8859_5 = {
"8859-5",
"ISO-8859-5",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -213,6 +217,7 @@
static QECharset charset_8859_6 = {
"8859-6",
"ISO-8859-6",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -255,6 +260,7 @@
static QECharset charset_8859_7 = {
"8859-7",
"ISO-8859-7|iso-ir-126|elot-928",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -296,6 +302,7 @@
static QECharset charset_8859_8 = {
"8859-8",
"ISO-8859-8",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -332,6 +339,7 @@
static QECharset charset_8859_9 = {
"8859-9",
"ISO-8859-9",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -374,6 +382,7 @@
static QECharset charset_8859_10 = {
"8859-10",
"ISO-8859-10",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -416,6 +425,7 @@
static QECharset charset_8859_11 = {
"8859-11",
"ISO-8859-11",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -458,6 +468,7 @@
static QECharset charset_8859_13 = {
"8859-13",
"ISO-8859-13|iso-ir-179|latin7|l7|iso-latin7",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -500,6 +511,7 @@
static QECharset charset_8859_14 = {
"8859-14",
"ISO-8859-14",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -534,6 +546,7 @@
static QECharset charset_8859_15 = {
"8859-15",
"ISO-8859-15|latin9|l9|latin0|l0",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -576,6 +589,7 @@
static QECharset charset_8859_16 = {
"8859-16",
"ISO-8859-16|latin10|l10",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -622,6 +636,7 @@
static QECharset charset_cp437 = {
"cp437",
"437",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -668,6 +683,7 @@
static QECharset charset_cp737 = {
"cp737",
"737",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -714,6 +730,7 @@
static QECharset charset_cp850 = {
"cp850",
"850",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -760,6 +777,7 @@
static QECharset charset_cp852 = {
"cp852",
"852",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -806,6 +824,7 @@
static QECharset charset_cp866 = {
"cp866",
"866",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -852,6 +871,7 @@
static QECharset charset_cp1125 = {
"cp1125",
"x-cp866-u|ruscii|1125",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -898,6 +918,7 @@
static QECharset charset_cp1250 = {
"cp1250",
"windows-1250|1250",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -944,6 +965,7 @@
static QECharset charset_cp1251 = {
"cp1251",
"windows-1251|1251",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -978,6 +1000,7 @@
static QECharset charset_cp1252 = {
"cp1252",
"windows-1252|1252",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1024,6 +1047,7 @@
static QECharset charset_cp1256 = {
"cp1256",
"windows-1256|1256",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1070,6 +1094,7 @@
static QECharset charset_cp1257 = {
"cp1257",
"windows-1257|1257",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1116,6 +1141,7 @@
static QECharset charset_mac_latin2 = {
"mac-latin2",
"x-mac-ce|mac-ce|macce|10029",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1162,6 +1188,7 @@
QECharset charset_mac_roman = {
"mac-roman",
"x-mac|mac",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1208,6 +1235,7 @@
static QECharset charset_kamen = {
"kamen",
"x-kam-cs|kam|867|869",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1254,6 +1282,7 @@
static QECharset charset_koi8_r = {
"koi8-r",
"",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1300,6 +1329,7 @@
static QECharset charset_koi8_u = {
"koi8-u",
"",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1362,6 +1392,7 @@
static QECharset charset_tcvn = {
"tcvn",
"TCVN-5712|TCVN|TCVN-0|TCVN-1",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1424,6 +1455,7 @@
static QECharset charset_viscii = {
"viscii",
"VISCII|VISCII-1|VISCII 1.1|VISCII-1.1|VISCII1.1-1",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1486,6 +1518,7 @@
static QECharset charset_cp037 = {
"cp037",
"037|ebcdic-037",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1548,6 +1581,7 @@
static QECharset charset_cp424 = {
"cp424",
"424|ebcdic-424",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1610,6 +1644,7 @@
static QECharset charset_cp500 = {
"cp500",
"500|ebcdic-500",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1672,6 +1707,7 @@
static QECharset charset_cp875 = {
"cp875",
"875|ebcdic-875",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1734,6 +1770,7 @@
static QECharset charset_cp1026 = {
"cp1026",
"1026|ebcdic-1026",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
@@ -1780,6 +1817,7 @@
static QECharset charset_atarist = {
"atarist",
"atari-st",
+ NULL,
decode_8bit_init,
decode_8bit,
encode_8bit,
Index: kmaptoqe.c
===================================================================
RCS file: /sources/qemacs/qemacs/kmaptoqe.c,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -b -r1.11 -r1.12
--- kmaptoqe.c 20 Apr 2008 14:18:18 -0000 1.11
+++ kmaptoqe.c 1 Mar 2014 22:37:26 -0000 1.12
@@ -2,7 +2,7 @@
* Convert Yudit kmap files to QEmacs binary internal format
*
* Copyright (c) 2002 Fabrice Bellard.
- * Copyright (c) 2007-2008 Charlie Gordon.
+ * Copyright (c) 2007-2014 Charlie Gordon.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
@@ -40,6 +40,7 @@
int len;
unsigned short output[20];
int olen;
+ int order;
} InputEntry;
static InputEntry inputs[NB_MAX];
@@ -55,6 +56,7 @@
static FILE *outfile;
static unsigned char outbuf[100000], *outbuf_ptr;
+/* sort function implements strict order, making qsort stable */
static int sort_func(const void *a1, const void *b1)
{
const InputEntry *a = a1;
@@ -66,7 +68,10 @@
if (val != 0)
return val;
}
- return a->output[0] - b->output[0];
+ val = a->output[0] - b->output[0];
+ if (val != 0)
+ return val;
+ return a->order - b->order;
}
@@ -496,8 +501,9 @@
InputEntry *ip;
if (argc < 3) {
- printf("usage: kmaptoqe outfile kmaps...\n"
- "Convert yudit keyboard maps to qemacs compressed format\n");
+ printf("kmaptoqe -- Convert yudit keyboard maps to qemacs compressed
format\n"
+ "usage: kmaptoqe outfile kmaps...\n"
+ " kmaptoqe --dump outfile\n");
exit(1);
}
if (!strcmp(argv[1], "--dump")) {
@@ -588,6 +594,7 @@
if (*p == '"')
break;
}
+ ip->order = ip - inputs;
ip++;
nb_inputs++;
continue;
Index: ligtoqe.c
===================================================================
RCS file: /sources/qemacs/qemacs/ligtoqe.c,v
retrieving revision 1.9
retrieving revision 1.10
diff -u -b -r1.9 -r1.10
--- ligtoqe.c 20 Apr 2008 14:18:19 -0000 1.9
+++ ligtoqe.c 1 Mar 2014 22:37:26 -0000 1.10
@@ -92,9 +92,13 @@
int val;
val = a->buf_in[0] - b->buf_in[0];
- if (val == 0 &&
- a->buf_in_size >= 2 && b->buf_in_size >= 2) {
+ if (val == 0
+ && a->buf_in_size >= 2 && b->buf_in_size >= 2) {
val = a->buf_in[1] - b->buf_in[1];
+ if (val == 0
+ && a->buf_in_size >= 3 && b->buf_in_size >= 3) {
+ val = a->buf_in[2] - b->buf_in[2];
+ }
}
return val;
}
Index: charsetjis.c
===================================================================
RCS file: /sources/qemacs/qemacs/charsetjis.c,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -b -r1.6 -r1.7
--- charsetjis.c 2 May 2008 17:05:39 -0000 1.6
+++ charsetjis.c 1 Mar 2014 22:37:26 -0000 1.7
@@ -145,6 +145,7 @@
static QECharset charset_euc_jp = {
"euc-jp",
NULL,
+ NULL,
decode_euc_jp_init,
decode_euc_jp_func,
encode_euc_jp,
@@ -224,6 +225,7 @@
static QECharset charset_sjis = {
"sjis",
NULL,
+ NULL,
decode_sjis_init,
decode_sjis_func,
encode_sjis,
Index: cptoqe.c
===================================================================
RCS file: /sources/qemacs/qemacs/cptoqe.c,v
retrieving revision 1.16
retrieving revision 1.17
diff -u -b -r1.16 -r1.17
--- cptoqe.c 1 Mar 2014 21:57:29 -0000 1.16
+++ cptoqe.c 1 Mar 2014 22:37:26 -0000 1.17
@@ -231,7 +231,8 @@
}
printf("\",\n");
- printf(" decode_8bit_init,\n"
+ printf(" NULL,\n"
+ " decode_8bit_init,\n"
" decode_8bit,\n"
" encode_8bit,\n"
" charset_get_pos_8bit,\n"
Index: ligatures
===================================================================
RCS file: /sources/qemacs/qemacs/ligatures,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -b -r1.1.1.1 -r1.2
Binary files /tmp/cvsNd7gZL and /tmp/cvsQrNYdn differ
Index: qe.h
===================================================================
RCS file: /sources/qemacs/qemacs/qe.h,v
retrieving revision 1.142
retrieving revision 1.143
diff -u -b -r1.142 -r1.143
--- qe.h 10 Feb 2014 21:27:53 -0000 1.142
+++ qe.h 1 Mar 2014 22:37:26 -0000 1.143
@@ -485,6 +485,7 @@
struct QECharset {
const char *name;
const char *aliases;
+ int (*probe_func)(QECharset *charset, const u8 *buf, int size);
void (*decode_init)(CharsetDecodeState *s);
int (*decode_func)(CharsetDecodeState *s);
/* return NULL if cannot encode. Currently no state since speed is
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [Qemacs-commit] qemacs charset.c charsetmore.c kmaptoqe.c ligto...,
Charlie Gordon <=